From Graph Diffusion to Graph Classification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913586002001920 |
|---|---|
| author | Xian, Jia Jun Cheng Mahdavi, Sadegh Liao, Renjie Schulte, Oliver |
| author_facet | Xian, Jia Jun Cheng Mahdavi, Sadegh Liao, Renjie Schulte, Oliver |
| contents | Generative models such as diffusion models have achieved remarkable success in state-of-the-art image and text tasks. Recently, score-based diffusion models have extended their success beyond image generation, showing competitive performance with discriminative methods in image {\em classification} tasks~\cite{zimmermann2021score}. However, their application to classification in the {\em graph} domain, which presents unique challenges such as complex topologies, remains underexplored. We show how graph diffusion models can be applied for graph classification. We find that to achieve competitive classification accuracy, score-based graph diffusion models should be trained with a novel training objective that is tailored to graph classification. In experiments with a sampling-based inference method, our discriminative training objective achieves state-of-the-art graph classification accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_17236 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From Graph Diffusion to Graph Classification Xian, Jia Jun Cheng Mahdavi, Sadegh Liao, Renjie Schulte, Oliver Machine Learning Artificial Intelligence Generative models such as diffusion models have achieved remarkable success in state-of-the-art image and text tasks. Recently, score-based diffusion models have extended their success beyond image generation, showing competitive performance with discriminative methods in image {\em classification} tasks~\cite{zimmermann2021score}. However, their application to classification in the {\em graph} domain, which presents unique challenges such as complex topologies, remains underexplored. We show how graph diffusion models can be applied for graph classification. We find that to achieve competitive classification accuracy, score-based graph diffusion models should be trained with a novel training objective that is tailored to graph classification. In experiments with a sampling-based inference method, our discriminative training objective achieves state-of-the-art graph classification accuracy. |
| title | From Graph Diffusion to Graph Classification |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2411.17236 |